Learn
How Hive works
Hive is an open source AI agent orchestration system. A fleet of specialized agents autonomously maintains software repositories — open source or private — triaging issues, writing fixes, opening PRs, and merging on green CI. A governor dynamically adjusts agent pace based on issue queue depth, and a deterministic pipeline gates every change.
Autonomy framework
The ACMM ladder
The AI-native Codebase Maturity Model (ACMM) defines six levels of AI agent autonomy, from advisory-only to fully autonomous. Each level controls which agents are active and what actions they can take. Start conservative, climb when you’re ready.
Advisory only
Agents analyze but don’t act. Beads and heartbeat logs only.
Issues, no PRs
Agents can open issues. Quality gates begin.
Hold-gated PRs
Agents open hold-gated PRs. CI must pass. Human approval required.
Merge on green
Agents open and merge PRs on green CI. Hold labels for safety.
Budget-aware
Full autonomy with budget controls. Governor manages pace and cost.
Multi-loop
Multi-loop orchestration. Outreach, community engagement. Highest trust.
The governor
Pace that follows your backlog
The governor senses queue depth and switches between four modes — idle, quiet, busy, and surge — each with its own per-agent cadences. A quiet repo costs almost nothing; a flooded queue gets the full fleet. Every change still passes the same deterministic gates.
Watchful
Empty queue. Agents sleep; sensing continues.
Steady
A few open issues. Slow, deliberate cadences.
Working
Queue is filling. Agents tighten their loops.
All hands
Critical backlog. Maximum cadence until drained.
The fleet
Specialized agents, one mission
Each agent owns a lane. Together they cover the maintenance lifecycle end to end — without stepping on each other’s work.
Agent health monitoring, sweep analysis, stall detection.
Triages issues, dispatches fixes, opens and merges PRs.
Documentation gaps, onboarding analysis, advisory reviews.
CI/CD health, workflow fixes, build monitoring.
Test coverage, integration tests, quality gates.
Security scanning, PR security gate.
Cross-cutting RFCs, refactors, new features.
Experiment design, A/B testing, strategy lab.
ADOPTERS outreach, community engagement.
On-demand ideation via Inception.
Under the hood
Built for trust
- GovernorDynamic mode switching (idle / quiet / busy / surge) with per-agent cadences.
- InceptionInteractive project scaffolding with llm-wiki and spec-kit.
- Knowledge BaseShared facts, wiki vaults, cross-agent priming.
- Audit LoggingAll state changes logged with who, when, and why.
- ACMM ProxyPer-agent HTTP proxy enforcing mode restrictions.
- ContributingCommunity agent contribution system with trust tiers.
Resources